docx-manipulation

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text and data to generate documents, which could allow malicious instructions within the input to influence agent behavior. * Ingestion points: User prompts for report generation, data tables, and contract placeholders. * Boundary markers: None defined to isolate or sanitize user-supplied content. * Capability inventory: Access to code_execution and file_operations tools. * Sanitization: No documented filtering or validation of user input before document insertion.
  • [EXTERNAL_DOWNLOADS]: The skill specifies the installation of the python-docx package from public registries.
  • [DYNAMIC_EXECUTION]: The skill generates and executes Python code at runtime to automate document formatting and creation tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 03:04 PM
Security Audit — agent-trust-hub — docx-manipulation